INDEX

Explanations

instances of the word 'driving'

oai_token-act-pair · gpt-3.5-turbo

instances of the word "driving" in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Flavoring

-0.99

 Seym

-0.76

reement

-0.76

ertain

-0.75

tle

-0.74

romeda

-0.74

Lum

-0.74

ANN

-0.72

ileaks

-0.72

ereo

-0.72

POSITIVE LOGITS

wheel

0.94

 driving

0.89

driving

0.89

boats

0.87

bike

0.83

 away

0.82

boat

0.80

 wheel

0.80

 simulator

0.79

 motorcycles

0.79

Activations Density 0.044%

instances of the word 'driving'

instances of the word "driving" in various contexts

No Comments

No Known Activations